Open-source evaluation toolkit of large vision-language models (LVLMs), support GPT-4v, Gemini, QwenVLPlus, 50+ HF models, 20+ benchmarks

Official Implementation of "Phishpedia: A Hybrid Deep Learning Based Approach to Visually Identify Phishing Webpages" USENIX'21

AI-Powered Camera-Trap Image Processing

OpenVINO™ is an open-source toolkit for optimizing and deploying AI inference

Dataset Management Framework, a Python library and a CLI tool to build, analyze and manage Computer Vision datasets.

《明日方舟》小助手，全日常一键长草！| A one-click tool for the daily tasks of Arknights, supporting all clients.

OrbbecSDK ROS wrapper

Collect some World Models for Autonomous Driving papers.

基于图像识别的自动化黑盒测试框架 | An automation black-box testing framework based on image recognition

Paper reading notes on Deep Learning and Machine Learning

An ASL detection script utilizing a TensorFlow image classification model trained from scratch. It is tailored to recognize American Sign Language (ASL) alphabet letters from live video streams, and provides documentation covering the neural network architecture, installation, dataset details, training procedures, and real-time detection.

An open survey on 3D Gaussian Splatting compression methods

我的AI学习笔记。包括b站up主deep_thoughts的PyTorch课程笔记和相关代码；北邮深度学习与数字视频PPT代码。

A multi-purpose camera system focused on offline license plate and object recognition

🍩 Extracting and processing information from receipts using Donut Model (OCR-free Document Understanding Transformer) https://github.com/clovaai/donut

Annotate better with CVAT, the industry-leading data engine for machine learning. Used and trusted by teams at any scale, for data of any scale.

📚 Jupyter notebook tutorials for OpenVINO™

Train, Evaluate, Optimize, Deploy Computer Vision Models via OpenVINO™

Find HALCON calibration board pattern from an image and extract center points in the circle grids array.